backend/query_llm.py

import os
from os import getenv

import gradio as gr
import requests

API_URL = getenv('API_URL')
BEARER = getenv('BEARER')

headers = {
    "Authorization": f"Bearer {BEARER}",
    "Content-Type": "application/json"
    }


def call_jais(payload):
    try:
        response = requests.post(API_URL, headers=headers, json=payload)
        response.raise_for_status()  # This will raise an exception for HTTP error codes
        return response.json()
    except requests.exceptions.HTTPError as http_err:
        raise gr.Error(f"An error occurred while processing the request. {http_err}")
    except Exception as err:
        raise gr.Error(f"An error occurred while processing the request. {err}")


def generate(prompt: str):
    payload = {'inputs': '', 'prompt': prompt}
    response = call_jais(payload)
    return response


def check_endpoint_status():
    # Replace with the actual API URL and headers
    api_url = os.getenv("ENDPOINT_URL")
    headers = {
        'accept': 'application/json',
        'Authorization': f'Bearer {os.getenv("BEARER")}'
        }

    try:
        response = requests.get(api_url, headers=headers)
        response.raise_for_status()  # will throw an exception for non-200 status
        data = response.json()

        # Extracting the status information
        status = data.get('status', {}).get('state', 'No status found')
        message = data.get('status', {}).get('message', 'No message found')

        return f"Status: {status}\nMessage: {message}"
    except requests.exceptions.RequestException as e:
        return f"Failed to get status: {str(e)}"